Related papers: Tumbug: A pictorial, universal knowledge represent…

Multimodal large language models (MLLMs), which integrate language and visual cues for problem-solving, are crucial for advancing artificial general intelligence (AGI). However, current benchmarks for measuring the intelligence of MLLMs…

While visual question-answering (VQA) benchmarks have catalyzed the development of reasoning techniques, they have focused on vertical thinking. Effective problem-solving also necessitates lateral thinking, which remains understudied in AI…

Analogical reasoning tests a fundamental aspect of human cognition: mapping the relation from one pair of objects to another. Existing evaluations of this ability in multimodal large language models (MLLMs) overlook the ability to compose…

Human-robot communication in situated environments involves a complex interplay between knowledge representations across a wide variety of modalities. Crucially, linguistic information must be associated with representations of objects,…

Causal generative modeling is essential for developing reliable and transparent AI systems capable of counterfactual reasoning. While existing approaches focus on integrating causal constraints during the training of generative models, they…

Evaluating creative text generation remains a challenge because existing reference-based metrics fail to capture the subjective nature of creativity. We propose a structured evaluation framework for AI story generation comprising four…

Retrieval-Augmented Generation (RAG) is a technique that enhances the capabilities of large language models (LLMs) by incorporating external knowledge sources. This method addresses common LLM limitations, including outdated information and…

Explainable AI seeks to bring light to the decision-making processes of black-box models. Traditional saliency-based methods, while highlighting influential data segments, often lack semantic understanding. Recent advancements, such as…

Reasoning, the ability to logically draw conclusions from existing knowledge, is a hallmark of human. Together with perception, they constitute the two major themes of artificial intelligence. While deep learning has pushed the limit of…

Knowledge Graphs (KGs) are crucial in the field of artificial intelligence and are widely used in downstream tasks, such as question-answering (QA). The construction of KGs typically requires significant effort from domain experts. Large…

Universal transformers (UTs) have been widely used for complex reasoning tasks such as ARC-AGI and Sudoku, yet the specific sources of their performance gains remain underexplored. In this work, we systematically analyze UTs variants and…

Humans use natural language to compose common concepts from their environment into plausible, day-to-day scene descriptions. However, such generative commonsense reasoning (GCSR) skills are lacking in state-of-the-art text generation…

Replicating AI research is a crucial yet challenging task for large language model (LLM) agents. Existing approaches often struggle to generate executable code, primarily due to insufficient background knowledge and the limitations of…

As artificial intelligence advances toward artificial general intelligence (AGI), the need for robust and human-like memory systems has become increasingly evident. Current memory architectures often suffer from limited adaptability,…

Visual Question Answering (VQA) focuses on providing answers to natural language questions by utilizing information from images. Although cutting-edge multimodal large language models (MLLMs) such as GPT-4o achieve strong performance on VQA…

The construction of artificial general intelligence (AGI) was a long-term goal of AI research aiming to deal with the complex data in the real world and make reasonable judgments in various cases like a human. However, the current AI…

Temporal knowledge graphs (TKGs) model the temporal evolution of events and have recently attracted increasing attention. Since TKGs are intrinsically incomplete, it is necessary to reason out missing elements. Although existing TKG…

As a technically challenging topic, visual storytelling aims at generating an imaginary and coherent story with narrative multi-sentences from a group of relevant images. Existing methods often generate direct and rigid descriptions of…

Retrieval-Augmented Generation (RAG) mitigates the hallucination problem of Large Language Models (LLMs) by incorporating external knowledge. Recursive summarization constructs a hierarchical summary tree by clustering text chunks,…

A fundamental challenge in artificial intelligence involves understanding the cognitive mechanisms underlying visual reasoning in sophisticated models like Vision-Language Models (VLMs). How do these models integrate visual perception with…